Krithika Rajendran

Krithika Rajendran

About

Detail

Actively Seeking Internship/Full-Time Opportunities Fall 2023 | Graduated from University of Texas at Arlington Summer 2023
Arlington, Texas, United States

Contact Krithika regarding: 
work
Full-time jobs
Starting at USD80K/year
connect_without_contact
Finding mentors
groups
Networking

Timeline


work
Job
school
Education
folder
Project (professional or personal)
flag
Award
auto_stories
Publication

Résumé


Jobs verified_user 0% verified
  • R
    Artificial Intelligence Engineer
    RadicalX
    Oct 2023 - Current (1 year 10 months)
    As an Artificial Intelligence Engineer at RadicalX, I am leveraging technologies such such as OpenAI and TensorFlow to develop an AI Dev Manager, create algorithms for personalized and adaptive learning, and devise robust anti-cheat and fraud detection systems
  • S
    Machine Learning Intern
    SoftStandard Solutions
    Feb 2023 - May 2023 (4 months)
    Collaborated in designing and developing AI-driven ML models using Instruction-Tuned LLMs and LangChain for OpenAI, which improved the accuracy of journal entry categorization by 40%. Implemented Python-based back-end systems and maintained the Django Rest Framework, enhancing the system’s efficiency and reliability. Developed, tested, and maintained SQL queries and dashboards for data analysis and visualization, leading to more streamlined data processing and interpretation. Built customer satisfaction prediction models for clients using distinctive algorithms, improving satisfaction predictions by approximately 35%. Actively communicated with clients to understand requirements and provide solutions, ensuring client satisfaction and smooth
  • Ballotpedia
    Data Engineer Intern
    Ballotpedia
    Sep 2022 - Dec 2022 (4 months)
    Streamlined Python scripts to scrape, clean, analyze and interpret electoral information from web/PDFs , adding a substantial volume of data to the database daily. Crafted an OCR tool using Easy-OCR and LayoutLM V3 models, effectively parsing complex ballot sheet images. Improved ETL workflow script efficiency by over 67% through Pythonic techniques and resolved a bottleneck. Maintained active contact with the client, taking regular feedback and implementing changes as necessary.
  • T
    System Engineer
    Tata Consultancy Services
    Dec 2015 - Jun 2018 (2 years 7 months)
    Big Data Stream , Hadoop Developer. Worked as a developer, tester in Big Data, Hadoop, Testing in varied projects of leading retailing, insurance and banking companies; Promoted as System Engineer Data Migration from Legacy Systems to Hive (Big Data): • Led the successful migration of data from legacy systems to Hive using advanced technologies such as Spark SQL, Hadoop, Kafka, and Delta Lake, ensuring seamless data transfer. Developed robust streaming pipelines for fraud detection and credit card approval, substantially reducing fraud alerts by 36%. Leveraged Hive for data analysis, developed UDFs, and optimized queries, reducing query processing time by nearly 40%. Won the “TCS Gems” Award for delivering exceptional results ahead of time
  • V
    Contract Web Developer
    Vijay Associates
    Dec 2013 - Jan 2014 (2 months)
    Develop a website with Jquery,PHP, Javascript with stylish and creative animations
Education verified_user 0% verified
  • T
    Master's degree, Computer Science
    The University of Texas at Arlington
    Aug 2021 - May 2023 (1 year 10 months)
  • Amrita Vishwa Vidyapeetham
    Bachelor of Technology (BTech, Computer Science
    Amrita Vishwa Vidyapeetham
    Jan 2011 - Jan 2015 (4 years 1 month)
  • L
    11,12 standard, Science Major
    Lakshmi SchoolVeerapanchan
    Jan 2009 - Jan 2011 (2 years 1 month)
  • T
    LKG-10TH Standard
    TVS Matriculation Higher Secondary SchoolMadurai
    Jan 1997 - Jan 2009 (12 years 1 month)
Projects (professional or personal) verified_user 0% verified
  • R
    Reflective Memory Bank using Deep Learning/Neural Networks
    Nov 2022 - Dec 2022 (2 months)
    Designed and developed a niche solution for a reflective Memory Bank System using Spark, PyTorch, and CNN-BiGRU for classifying themes/topics on individual journal entries. Annotated entries using LightTag AI API. with Glove Embedding [https://bit.ly/multi_label_classification_cnn_bigru]. Data Annotation using Light Tag app and exported as JSON as input. The predictive model will be deployed using Flask, and new data will be fed back to the model. [ https://medium.com/@rkrithika1993/reflective-memory-bank-6960c634f818] Achieved an impressive 97% AUC metric accuracy on the first attempt in the test dataset, contributing to accurate input prediction based on patterns from past data.
  • B
    Big Data using Hadoop MapReduce Scala and Spark Scala
    Mar 2022 - May 2022 (3 months)
    Delivered 50%+ efficiency boost by optimizing Graph Dynamic partitioning-based Substructure and Isomorphs Discovery, leveraging performance tuning using multiple Mappers and Reducers, Parquet files, and Google Cloud deployment for large datasets. Implemented Graph Isomorphism Network on top of the data for finding isomorphs. Working on Massively Large datasets in academic projects to extract valuable insights and create visualizations. Employed distributed, scalable Spark Scala architecture, Scala MapReduce to increase the efficiency of Algorithms originally used in IT Lab at UTA.
  • C
    Chatbot using Machine Learning and Deep Learning
    Oct 2019 - Feb 2020 (5 months)
  • N
    NYC Taxi Dataset , Checking the accuracy and predicting optimal trip time using Logistic Regression
    Oct 2019
  • W
    Word Embeddings in Keras Library using Python for Software Engineering Documents Similarity
    Oct 2018 - Dec 2018 (3 months)
    Performed Word Embeddings in Keras Library using Python for Software Engineering Documents and measuring their document similarity with Queries(SE related code) and performing Ranking using Semantic Vectors Package as well as XGboost Learning to Rank.This project is basically for learning more about Information Retrieval in Software Engineering for improving the results for query in use cases like Bug reports, Linking software API documents to stackoverflow answers, evaluation of pseudo code type answers.
  • S
    Short Answer Grading System Using Classification And Clustering(Final Year Project)
    Jan 2015 - Jul 2015 (7 months)
    Made to predict whether new student answers are correct or not with Scored Labels, Scored Probabilities and cluster the student answers among themselves and provide them with feedback,find similarity between sentences, using Natural Language Processing packages like NLTK, Semantic Vectors Package, Machine Learning techniques, Wikipedia based ESA. The programming language used was Python.The Machine Learning Techniques were implemented in Microsoft Azure Machine Learning Studio. This enables to provide contextual feedback to improve the coding skills of people. I also integrated Jython (for Stanford Tree Dependency Parser in 2015) and Python for this Project. I also have worked on Threads and Parallel Processing with the Project to include
  • D
    Data Analysis & Visualization
    Volunteered to help Professor in a Data Science workshop in Python by creating visualizations like Word Cloud using Tableau for Top hubs for major Airlines using the NetworkX package. Generated visualization reports and extracted insights and recommendations on the best time to start campaigns using the Kickstarter funding campaigns dataset.
  • S
    Spark_Scala_Substructure_Discovery
    Worked on Graph data transformation, conversion, and computation, successfully translating over 1000 lines of code from Java to Scala for Graph Partitioning Algorithms with a Dynamic Adjacency List for Substructure duplicate detection in both Spark-Scala and MapReduce Scala. Tracked KPIs such as runtime in Google Cloud Platform among Spark Scala, MapReduce Scala, Spark Java, and MapReduce Java Optimized application performance by implementing best coding practices, resulting in a 30% increase in processing speed by utilizing parquet files in Spark to streamline data storage and retrieval processes.
Awards verified_user 0% verified
  • A
    Innovation Jockeys Jury's Choice Award
    Accenture India Private Limited Yahoo
    Nov 2015
    I won Jury Choice Award for my Innovation in Cognitive Computing and Internet Of Things for my final year project titled "Innovative Divide and Conquer for a Novel Purpose" based on machine learning and natural language processing.https://in.news.yahoo.com/meet-the-winners-of-innovation-jockey-season-4-235138356.html http://inspiration.innovationjockeys.net/post/145366612582/coding-all-the-way
Publications verified_user 0% verified
  • P
    Learning to Grade Short Answers using Machine Learning Techniques
    Proceedings Of Third International Symposium on Women in Computing and InformaticsACM Digital Library International Conference Proceeding SeriesISBN No 9781450333610
    Jan 2015